Viewing profile — nnx
nnx
HN member- Joined
- Tue, Dec 17, 2013, 12:02 PM UTC
- HN karma
- 6,153
- Public activity
- 854 items
- HN profile
- View on Hacker News ↗
About nnx
Recent public activity
- story
- story
-
comment
Comment #49093755
is flickering fully fixed yet?
- story
- story
- story
-
comment
Comment #48512848
Not saying there's no negative impacts, but what are the _huge_ negative impacts that have materialized so far?
- story
- story
- story
- story
- story
-
comment
Comment #47861683
Coincidentally this is how pretraining works :)
-
comment
Comment #47824240
Looks really interesting but the Go binding sadly uses cgo. Could the binding be done in pure Go? Or at least purego (the cgo alternative using Go assembly for FFI) ?
- story
-
comment
Comment #47789394
I ended up just using the web version, which is actually better than the native app (multiple tabs works!).
-
comment
Comment #47789287
> My M5 Pro can generate 130 tok/s (4 streams) on Gemma 4 26B. This seems high. At which quantization? Using LM Studio or something else? Note: Darkbloom seems to run everything on…
- story
-
comment
Comment #47610822
The only limit is yourself!
- story
- story
- story
- story
- story
-
comment
Comment #47359913
Are you `Ionstream` on OpenRouter? If so, it would be great to provide more models through OpenRouter. This looks interesting but not enough to make me go through the trouble of se…